Voice Mode
About
Voice Mode brings natural voice conversations to AI assistants like Claude through the Model Context Protocol (MCP).
Details
- Author
- mbailey
- Downloads
- 246
- Categories
- Communication, Other, AI
Jump to
- Real‑time voice interactions with AI
- Works with Claude Desktop and other MCP clients
- Supports local microphone and LiveKit rooms
- OpenAI‑compatible STT and TTS integration
- Low‑latency, natural conversations
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
Voice ModeCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
Install the package with pip install voice-mode or uvx voice-mode, then add it to your Claude Desktop configuration. After setup, you can start talking to your AI assistant.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"voice mode": {
"voice-mode": {
"type": "stdio",
"command": "uvx",
"args": [
"--refresh",
"."
],
"env": {
"OPENAI_API_KEY": "XXXXXX"
}
}
}
}
}McpServers
{
"voice-mode": {
"type": "stdio",
"command": "uvx",
"args": [
"--refresh",
"."
],
"env": {
"OPENAI_API_KEY": "XXXXXX"
}
}
}Natural voice conversations with Claude Code (and other MCP capable agents)
VoiceMode enables natural voice conversations with Claude Code. Voice isn't about replacing typing - it's about being available when typing isn't.
- Walking to your next meeting
- Cooking while debugging
- Giving your eyes a break after hours of screen time
- Holding a coffee (or a dog)
- Any moment when your hands or eyes are busy
Requirements:Computer with microphone and speakers
Option 1: Claude Code Plugin (Recommended)
The fastest way for Claude Code users to get started:
# Add the VoiceMode marketplace claude plugin marketplace add mbailey/voicemode # Install VoiceMode plugin claude plugin install voicemode@voicemode ## Install dependencies (CLI, Local Voice Services) /voicemode:install # Start talking! /voicemode:converse
Installs dependencies and the VoiceMode Python package.
# Install UV package manager (if needed) curl -LsSf https://astral.sh/uv/install.sh | sh # Run the installer (sets up dependencies and local voice services) uvx voice-mode-install # Add to Claude Code claude mcp add --scope user voicemode -- uvx --refresh --from voice-mode voicemode-mcp-launcher # Optional: Add OpenAI API key as fallback for local services export OPENAI_API_KEY=your-openai-key # Start a conversation claude converse
For manual setup, see theGetting Started Guide.
- Natural conversations- speak naturally, hear responses immediately
- Works offline- optional local voice services (Whisper STT, Kokoro TTS)
- Low latency- fast enough to feel like a real conversation
- Smart silence detection- stops recording when you stop speaking
- Privacy options- run entirely locally or use cloud services
Platforms:Linux, macOS, Windows (native or WSL), NixOSPython:3.10-3.14
VoiceMode works out of the box. For customization:
# Set OpenAI API key (if using cloud services) export OPENAI_API_KEY="your-key" # Or configure via file voicemode config edit
See theConfiguration Guidefor all options.
To use VoiceMode without permission prompts, add to~/.claude/settings.json:
{ "permissions": { "allow": [ "mcp__voicemode__converse", "mcp__voicemode__service" ] } }
See thePermissions Guidefor more options.
For privacy or offline use, install local speech services:
- Whisper.cpp- Local speech-to-text
- Kokoro- Local text-to-speech with multiple voices
These provide the same API as OpenAI, so VoiceMode switches seamlessly between them.
sudo apt update sudo apt install -y ffmpeg gcc libasound2-dev libasound2-plugins libportaudio2 portaudio19-dev pulseaudio pulseaudio-utils python3-dev
WSL2 users: The pulseaudio packages above are required for microphone access.
sudo dnf install alsa-lib-devel ffmpeg gcc portaudio portaudio-devel python3-devel
# Use development shell nix develop github:mbailey/voicemode # Or install system-wide nix profile install github:mbailey/voicemode
git clone https://github.com/mbailey/voicemode.git cd voicemode uv tool install -e .
# In /etc/nixos/configuration.nix environment.systemPackages = [ (builtins.getFlake "github:mbailey/voicemode").packages.${pkgs.system}.default ];
export VOICEMODE_SAVE_AUDIO=true # Files saved to ~/.voicemode/audio/YYYY/MM/
- Getting Started- Full setup guide
- Configuration- All environment variables
- Whisper Setup- Local speech-to-text
- Kokoro Setup- Local text-to-speech
- Development Setup- Contributing guide
- Website:voicemode.dev
- GitHub:github.com/mbailey/voicemode
- PyPI:pypi.org/project/voice-mode
- YouTube:@getvoicemode
- Twitter/X:@getvoicemode
- Newsletter:
Upfirst is an AI phone receptionist for small businesses. Review call transcripts, then fix the greeting, knowledge, and transfer rules from your AI client.
Provides audio input and output capabilities for AI assistants.
Enables communication between multiple AI characters with simultaneous voice playback using VLC.
An MCP server integrating WhatsApp messaging and ElevenLabs AI voice capabilities into VS Code.
Multilingual intelligence + memory + safety + voice layer for autonomous AI agents
Interact with RetellAI's voice services to create conversational voice AI.
Integrate AI assistants with VOYP's calling capabilities to make calls, search business info, and manage call status.
Voice AI assistant builder for websites — create and deploy AI voice bots that respond in 50+ languages, 24/7.
A voice-enabled AI personal assistant that integrates multiple tools and services through natural voice interactions using MCP.
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
